© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93853
    Prev
    Next
    INDEX
    Explanations

    usual or general descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possibly
    -2.11
     parfois
    -1.86
     иногда
    -1.84
     eventuell
    -1.84
     potentially
    -1.71
     возможно
    -1.63
    possibly
    -1.62
     soms
    -1.59
     mohou
    -1.55
     teilweise
    -1.54
    POSITIVE LOGITS
     only
    1.94
     either
    1.71
     found
    1.52
    Either
    1.46
    either
    1.45
     Either
    1.39
     irgendwo
    1.37
     suele
    1.33
     accompanied
    1.32
     more
    1.30
    Activations Density 0.169%

    No Known Activations